Real-Time multi-objective optimization of safety and mobility at signalized intersections

Adaptive Traffic Signal Control (ATSC) is becoming a popular dynamic traffic management technique, especially with the emerging connected vehicles (CVs) technology. ATSC algorithms have been extensively considered in the literature for enhancing traffic mobility at signalized intersections. However, improving safety has rarely been used as an objective in existing ATSC algorithms. To fill this gap, this paper proposes a multi-criteria reinforcement learning based ATSC algorithm with two optimization objectives: real-time safety and mobility. The algorithm was trained on both objectives using traffic simulation. The safety objective was considered using extreme value theory (EVT) real-time crash risk evaluation models. Reducing the total intersection delay was the mobility objective. Different weights were considered in the training to account for both objectives simultaneously. The performance of the trained algorithm was then validated using real-world video data. Results show that the proposed multi-objective algorithm can improve both safety and mobility even under lower weights.

Automated summary

This paper proposes a multi-criteria reinforcement learning based ATSC algorithm, aiming to improve both traffic safety and mobility. The algorithm was trained and validated using real-time traffic simulation and extreme value theory models, showing significant improvements in safety and mobility.